Differentially Private Active Learning with Latent Space Optimization

Existing Active Learning (AL) schemes typically address privacy in the narrow sense of furnishing a differentially private classifier. Private data are exposed to both the labeling and learning functions, a limitation that necessarily restricts their applicability to a single entity. In this paper, we propose an AL framework that allows the use of untrusted parties for both labeling and learning, thereby allowing joint use of data from multiple entities without trust relationships. Our method is based on differentially private generative models and an associated novel latent space optimization scheme that is more flexible than the traditional ranking method. Our experiments on three datasets (MNIST, CIFAR10, CelebA) show that our proposed scheme produces better or comparable results than state-of-the-art techniques on two different acquisition functions (VAR and BALD).